# SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting

arXiv: https://arxiv.org/abs/2605.12992 · HTML: https://mlsanity.com/paper/2605.12992/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 11 of 11)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Resurrecting Recurrent Neural Networks for Long Sequences](https://mlsanity.com/paper/2303.06349/) (2023)
- [HGRN2: Gated Linear RNNs with State Expansion](https://mlsanity.com/paper/2404.07904/) (2024)
- [A Unified, Scalable Framework for Neural Population Decoding](https://mlsanity.com/paper/2310.16046/) (2023)
- [Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity](https://mlsanity.com/paper/2109.04463/) (2021)
- [Representation learning for neural population activity with Neural Data Transformers](https://mlsanity.com/paper/2108.01210/) (2021)
- [LaSNN: Layer-wise ANN-to-SNN Distillation for Effective and Efficient Training in Deep Spiking Neural Networks](https://mlsanity.com/paper/2304.09101/) (2023)
- [BRAID: Input-Driven Nonlinear Dynamical Modeling of Neural-Behavioral Data](https://mlsanity.com/paper/2509.18627/) (2025)
- [POCO: Scalable Neural Forecasting through Population Conditioning](https://mlsanity.com/paper/2506.14957/) (2025)

## Built on by (most cited first, 2 of 2)

- [Stochastic Flow Map for Count Data](https://mlsanity.com/paper/2609.23290/) (2026)
- [A discrete generative model of neuronal spiking activity on microelectrode arrays](https://mlsanity.com/paper/2609.23907/) (2026)

## Abstract (arXiv)

Neural population models, which predict the joint firing of many simultaneously recorded neurons forward in time, are typically evaluated by a single aggregate Pearson correlation r between predicted and actual spike counts, a number that masks critical structure. We argue that how we evaluate spike forecasting matters as much as what we build, and introduce SpikeProphecy, the first large-scale benchmark for causal, autoregressive spike-count forecasting on real electrophysiology recordings. Our core contribution is a population metric decomposition that separates aggregate performance into temporal fidelity, spatial pattern accuracy, and magnitude-invariant alignment. The decomposition surfaces aspects of the underlying data that an aggregate scalar collapses together. We apply the protocol to 105 Neuropixels sessions (Steinmetz 2019 + IBL Repeated Site; ~89,800 neurons) with seven architecture baselines spanning four structural families: four SSMs (three diagonal and one non-diagonal), a Transformer, an LSTM, and a spiking network. The decomposition surfaces a brain-region predictability ranking that reproduces across all seven baselines and survives ANCOVA correction for firing-statistics constraints (region Delta R2 = 0.018 above the firing-statistics covariates). It also exposes a sub-Poisson evaluation floor where rigorous metrics combine with genuine biophysical constraints on regular spike trains, and yields a negative result on KL-on-output-rates distillation for ANN-to-SNN transfer in this Poisson count domain.